AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Multi-marginal temporal Schrödinger Bridge Matching from unpaired data

Thomas Gravier, Thomas Boyer, Auguste Genovesio

ICML 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Flow matching generative modeling · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use MMtSBM instead of the previous best comparable SB method [SF]2M-GeoMMtSBM · MULTI d=100W1: 52.203 -> 44.542Improved
use MMtSBM instead of DMSBMMtSBM · Embryoid Body d=100 (all marginals)MMD: 0.032 -> 0.019Improved
use MMtSBM instead of DMSBMMtSBM · Embryoid Body d=100 (all marginals)SWD: 0.16 -> 0.130Improved
use MMtSBM instead of 3MSBM on held-out timesMMtSBM · Embryoid Body d=100 (held-out)MMD t3: 0.14 -> 0.06Improved
add SB learning phase (IMFF) after flow-matching warm-up (ablation)MMtSBM · 2D Gaussian mixtures N=3trajectory optimalityImproved
use naive (non-factorized) multi-marginal IMF (ablation)IMF extension · multi-marginal convergenceconvergenceHurt
train multi-marginal bridge instead of single bridgeMMtSBM · Moons (N=4)W2: 0.144 -> 0.148No clear effect
run SB phase after warm-up in 50d Gaussian transport (ablation)MMtSBM · 50d Gaussian multi-marginalcovarianceImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy